Interim analysis of sequential estimation‐adjusted urn models with sample size re‐estimation

Abstract

Clinical trials usually involve efficient and ethical objectives. Different adaptive designs have been proposed to satisfy these needs. We combine interim analysis, the sequential estimation-adjusted urn model (SEU), and sample size re-estimation (SSR) in one clinical trial. We show that the asymptotic distribution, under the null hypothesis, of the proposed sequential statistic follows Brownian motion by simultaneously addressing the three sequential procedures (allocation of patients, urn composition, and sequential parameter estimators) and the sequential statistics with revised information time due to SSR. Therefore, to control the type I error rate, traditional critical values for sequential monitoring based on Brownian motion can be used for the proposed procedure. Numerical studies with three types of urn models demonstrate that our proposed approach can control the type I error rate well and also achieve efficient and ethical objectives.

Seamless Clinical Trials with Doubly Adaptive Biased Coin Designs

“…This paper opens the door to future research topics. First, there are two families of RAR designs, DBCD and urn models [64,65,72]. It is worth exploring the seamless clinical trials with urn models.…”

“…Clinical trials are complex and usually have multiple objectives such as increasing the power of detecting treatment differences, and assigning more patients to better treatments. Two families of RAR have been proposed to achieve these objectives: DBCD [25,62,70,71] and urn models [64,65,69,72]. RAR can achieve greater efficiency and ethical advantages by skewing the allocation proportion based on previous treatment assignments and responses.…”